In this paper, an object characterization method based on neural networks is developed for GPR subsurface imaging. Currently, most existing studies demonstrate detecting and imaging objects of cylindrical shapes. While in this paper, no restriction is imposed on the object shape. Three neural network algorithms are exploited to characterize different types of object signatures, including object shape, object material, object size, object depth and subsurface medium’s dielectric constant. Feature extraction is performed to characterize the instantaneous amplitude and time delay of the reflection signal from the object. The characterization method is evaluated utilizing the data synthesized with the finite-difference timedomain (FDTD) simulator.
Yu Zhang, Dryver Huston, and Tian Xia, "Underground object characterization based on neural networks for ground penetrating radar data," Proc. SPIE 9804, Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016, 980403 (Presented at SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring: March 21, 2016; Published: 8 April 2016); https://doi.org/10.1117/12.2219345.
Conference Presentations are recordings of oral presentations given at SPIE conferences and published as part of the proceedings. They include the speaker's narration with video of the slides and animations. Most include full-text papers. Interactive, searchable transcripts and closed captioning are now available for 2018 presentations, with transcripts for prior recordings added daily.
Search our growing collection of more than 16,000 conference presentations, including many plenaries and keynotes.